ONNX Model Zoo

onnx-community/AFM-4.5B-ONNX

By onnx-community · ↓ 2 · ♥ 4 · Updated 2025-09-17

What's in this repo

This page lists the files in onnx-community/AFM-4.5B-ONNX, including model_q4.onnx, model_q4f16.onnx.

  • 2 ONNX models (.onnx files)
  • 15 files, including 5 .json, 2 .onnx, 2 .onnx_data, 2 .onnx_data_1, 1 .md, 1 .jinja
  • Last updated 2025-09-17

ONNX files

File Size Download
onnx/model_q4.onnx — Download
onnx/model_q4f16.onnx — Download

How to use

These ONNX files can be loaded with ONNX Runtime. To inspect a model graph, upload the file to the Netron viewer. Download links point to the original files on Hugging Face.

README

Usage (Transformers.js)

If you haven't already, you can install the Transformers.js JavaScript library from NPM using:

npm i @huggingface/transformers

You can then generate text as follows:

import { pipeline, TextStreamer } from "@huggingface/transformers";

// Create a text generation pipeline
const generator = await pipeline(
  "text-generation",
  "onnx-community/AFM-4.5B-ONNX",
  { dtype: "q4f16" },
);

// Define the list of messages
const messages = [
  { role: "system", content: "You are a helpful assistant." },
  { role: "user", content: "What is the capital of France?" },
];

// Generate a response
const output = await generator(messages, {
    max_new_tokens: 512,
    do_sample: false,
    streamer: new TextStreamer(generator.tokenizer, { skip_prompt: true, skip_special_tokens: true }),
});
console.log(output[0].generated_text.at(-1).content);

Model info

text-generation transformers.js
transformers.js onnx arcee text-generation conversational en es fr de it pt ru
↓ 2 ♥ 4

Created: 2025-07-30

Updated: 2025-09-17

View on Hugging Face

Files (15)

.gitattributes
LICENSE
README.md
chat_template.jinja
config.json
generation_config.json
onnx/model_q4.onnx ONNX
onnx/model_q4.onnx_data
onnx/model_q4.onnx_data_1
onnx/model_q4f16.onnx ONNX
onnx/model_q4f16.onnx_data
onnx/model_q4f16.onnx_data_1
special_tokens_map.json
tokenizer.json
tokenizer_config.json

Related models